norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers2 hours ago
ResearchDaily Papers

A Zeroth-Order Paradigm for LLM Preference Alignment

This paper introduces Comparison-based Preference Optimization (ComPO), a zeroth-order method for aligning large language models with human preferences by using comparison oracles to extract directional information from preference pairs without direct optimization of a differentiable loss. The method includes offline and online variants with convergence and performance guarantees, showing improvements over existing alignment methods in experiments with various models.

Open original
SIGNAL FROM THE SOURCE
21
source votes
Tracking sinceSeptember 17, 202621 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 16, 2026Peter Chen, Xi Chen, Wotao Yin
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

21 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

This method offers a new approach to aligning language models with human preferences without relying on direct optimization of a differentiable loss function, which could be useful in scenarios where such optimization is challenging or impractical.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

StepAudio 3 Realtime Technical Report

StepAudio 3 Realtime is an audio-language foundation model designed for real-time spoken interaction, featuring a continuous listen-converse-think-act loop. It includes Deep Perception for interpreting user intent, Seamless Duplex for handling audio stream synchronization, and Think-While-Speaking to balance reasoning and latency. The model achieves high performance on benchmarks like MMSU and Artificial Analysis Full-Duplex, along with a task-success rate on τ-Voice.

5 days agoDaily Papers

StepAudio 3 Music: Large-Scale Music Generation with Explicit Planning and Text Control

StepAudio 3 Music is a large-scale music generation model that uses explicit musical planning and text control. It employs a flow-matching diffusion Transformer to predict audio latents, with a discrete-continuous design and a Mixture-of-Experts autoregressive model for structured music generation.

6 days agoDaily Papers

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

PhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.

3 days agoDaily Papers

LynnReal-Omni: Native Multi-Modal Video Generation for Agentic Visual Workflows

LynnReal-Omni is a native multimodal video generation framework that combines text-to-video, image-conditioned generation, and structural control into a single model. It includes a 32B shared multimodal diffusion transformer and a 27B Flash version for real-time rendering, with a data pipeline and evaluation method designed for video generation tasks.

3 days agoDaily Papers

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

The paper introduces XConf, a method for estimating confidence in language models by leveraging the model's accumulated experience. XConf uses past episodes, including tasks, reflections, confidence levels, outcomes, and lessons learned, to inform current confidence estimates through a recall and reflect process. It outperforms existing methods in discrimination and calibration with lower computational cost.

2 days agoDaily Papers

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

ZGCM-1 is a 7B parameter foundation model designed for math and agentic search, emphasizing efficiency through architectural and system co-design, progressive curriculum learning, and an AI-native R&D workflow. It demonstrates competitive performance against larger models on mathematical and search tasks, with improvements in training efficiency and open-source availability of training materials.

6 days ago